robustness

The FRIES Trust Score: How AI Trustworthiness Can Be Quantified

11. June 2025

How can the trustworthiness of AI models be measured objectively and systematically? The FRIES Trust Score offers a structured approach to enhance transparency and comparability in models and datasets....

Plants don’t walk on the street: Using human knowledge for reliable semantic segmentation

Linara Adilova,

17. November 2021

Data-driven sensor interpretation in autonomous driving can sometimes lead to very implausible predictions. A partly human-designed, partly learned rule set can make existing deep neural networks that process low-level sensor information reliable....

Robust Linear Regression for Machine Learning

Pascal Welke,

08. September 2021

The method of least absolute deviation can be used to determine a regression line and train a linear regression model so that it is robust against irregularities - so-called “outliers” - in the data....

Robust or vulnerable – gaining more insights into neural networks with heat

Lukas Franken, Dr. Bogdan Georgiev,

01. June 2021

How easily AI algorithms can be attacked depends on the shape of the boundaries with which the neural network separates decisions from each other. This can be determined by heating up the decision boundaries....